> For the complete documentation index, see [llms.txt](https://releases.pipekit.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://releases.pipekit.io/v6/v6.66.4.md).

# v6.66.4

### 2026-05-27

### What's Changed

#### New Features 🎉

* feat(mcp): add fields summary|full and rename nodeName→nodeID on get\_workflow\_node
* feat(mcp): add fields summary|full mode to get\_run and cross-link sibling tools
* feat(mcp): add serviceAccount/entryPoint/labels/annotations on submit\_workflow
* feat(mcp): tune cron tool descriptions and standardise on workflowName
* feat: Add AI assistant sidebar (BYOK + Pipekit MCP)
* feat(mcp): group get\_run\_logs output, add compact mode and truncationReason

#### Patches 🩹

* chore(mcp): tighten run-action descriptions; prep client for retry
* feat(mcp): emit CORS headers for browser callers
* fix(mcp): allow User-Agent in CORS preflight

#### Bug Fixes and Dependency Updates 🐞

***

### About Pipekit

Pipekit is the control plane for Argo Workflows. Platform teams use Pipekit to manage data & CI pipelines at scale, while giving developers self-serve access to Argo. Pipekit's unified logging view, Workflow Metrics dashboards, enterprise-grade RBAC and multi-cluster management capabilities lower maintenance costs for platform teams while delivering a superior devex for Argo users. Sign up for a 30-day free trial at [pipekit.io/signup](https://pipekit.io/signup?utm_campaign=release-notes).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://releases.pipekit.io/v6/v6.66.4.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.